Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Efficient classification of images with taxonomies

: Binder, A.; Kawanabe, M.; Brefeld, U.


Zha, H.; Taniguchi, R.; Maybank, S.:
Computer Vision - ACCV 2009 : 9th Asian Conference on Computer Vision, Xi'an, China, September 23 - 27, 2009. Revised selected papers, part III
2010 (Lecture Notes in Computer Science 5996)
ISBN: 978-3-642-12297-2
ISBN: 978-3-642-12296-5 (print)
ISSN: 0302-9743
Asian Conference on Computer Vision (ACCV) <9, 2009, Xi'an>
Conference Paper
Fraunhofer FIRST ()

We study the problem of classifying images into a given, pre-determined taxonomy. The task can be elegantly translated into the structured learning framework. Structured learning, however, is known for its memory consuming and slow training processes. The contribution of our paper is twofold: Firstly, we propose an e.cient decomposition of the structured learning approach into an equivalent ensemble of local support vector machines (SVMs) which can be trained with standard techniques. Secondly, we combine the local SVMs to a global model by re-incorporating the taxonomy into the training process. Our empirical results on Caltech256 and VOC2006 data show that our local-global SVM effectively exploits the structure of the taxonomy and outperforms multi-class classification approaches.